dbcve.org
Open WebuiApplication · Openwebui

CVE-2026-44556

HIGH · 7.1 CVSS v3.1 Published 2026-05-15
Fix available
A fix is available. Upgrade to 0.9.0 or later.
See remediation →
77/100
Remediation priority · High
Remotely reachable Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.0, the /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint (generate_chat_completion) checks model ownership, group membership, and AccessGrants before allowing a request, the /responses proxy only validates that the user has a valid session via get_verified_user. This allows any authenticated user to interact with any model configured on the instance by sending a POST request to /api/openai/responses with an arbitrary model ID. This vulnerability is fixed in 0.9.0.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

Open WebUI versions before 0.9.0 have an authorization bypass in the /responses endpoint (POST /api/openai/responses). Unlike the primary chat completion endpoint which enforces model ownership, group membership, and AccessGrants, the /responses proxy only validates user authentication via get_verified_user. This allows any authenticated user to interact with any configured model by specifying an arbitrary model ID in the request.

MitigationUpgrade Open WebUI to version 0.9.0 or later, which implements proper per-model access control on the /responses endpoint.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Open WebuiApplication
Affected:< 0.9.0

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
None
Availability
High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Determine installed Open WebUI version
    Check the running container image tag, or inspect the UI footer for the version number, or query the /api/v1/info endpoint if available
    Affected if The version is below 0.9.0
  2. Identify if /responses endpoint is exposed
    Verify the POST /api/openai/responses endpoint is accessible in your deployment by reviewing your reverse proxy configuration or API gateway routes
    Affected if The endpoint is publicly or broadly accessible without additional network restrictions
  3. Test authorization on the /responses endpoint
    Using an authenticated user account with limited model access, send a POST request to /api/openai/responses with a model ID that the user should NOT have access to (a model configured for other users or groups)
    Affected if The request succeeds and returns a valid response instead of being denied based on model ownership or AccessGrants
  4. Compare endpoint security to chat completions
    Send identical model access requests to both /v1/chat/completions and /api/openai/responses using a restricted user account; verify if they enforce the same authorization checks
    Affected if /v1/chat/completions properly denies unauthorized model access while /api/openai/responses allows it

You are affected if running Open WebUI version below 0.9.0 AND the /api/openai/responses endpoint permits authenticated users to access models they should not have permission to use.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Upgrade available Upgrade to 0.9.0 or later
Fixed in 0.9.0
Interim mitigation

Upgrade Open WebUI to version 0.9.0 or later, which implements proper per-model access control on the /responses endpoint.

Recommended fix High confidence

0.9.0

  1. Upgrade Open WebUI to version 0.9.0 or later
  2. After upgrading, verify that the /api/openai/responses endpoint now properly enforces per-model access control
  3. Test that users can only access models they have been granted permission to use

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Open Webui Scoped from the published advisory
  • Consultation3.0 h
  • Implementation4.0 h
  • Testing3.0 h
  • Review / QA2.0 h
12.0 hours of engineering $2,130
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,408.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-44556 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-44556 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data